-
Notifications
You must be signed in to change notification settings - Fork 62
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
129e7c3
commit 117ae31
Showing
4 changed files
with
27 additions
and
197 deletions.
There are no files selected for viewing
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,39 +1,33 @@ | ||
| theme: default # default || dark | ||
| organization: OMRON SINIC X | ||
| twitter: '@omron_sinicx' | ||
| title: 'Multi-Agent Behavior Retrieval: Retrieval-Augmented Policy Training for Cooperative Manipulation by Mobile Robots' | ||
| conference: IROS2024 | ||
| title: 'MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics' | ||
| conference: IJCAI2020 | ||
| resources: | ||
| paper: https://arxiv.org/abs/1909.13111 | ||
| code: https://github.com/omron-sinicx/multipolar | ||
| video: https://www.youtube.com/embed/W8nBFKDxsb0 | ||
| video: https://www.youtube.com/embed/adUnIj83RtU | ||
| blog: https://medium.com/sinicx/multipolar-multi-source-policy-aggregation-for-transfer-reinforcement-learning-between-diverse-bc42a152b0f5 | ||
| demo: https://colab.research.google.com/ | ||
| huggingface: https://huggingface.co/ | ||
| demo: | ||
| huggingface: | ||
| description: explore a new challenge in transfer RL, where only a set of source policies collected under unknown diverse dynamics is available for learning a target task efficiently. | ||
| image: https://omron-sinicx.github.io/${your-repository-name}/teaser.png | ||
| url: https://omron-sinicx.github.io/${your-repository-name} | ||
| image: https://omron-sinicx.github.io/multipolar/teaser.png | ||
| url: https://omron-sinicx.github.io/multipolar | ||
| speakerdeck: b7a0614c24014dcbbb121fbb9ed234cd | ||
| authors: | ||
| - name: So Kuroki | ||
| - name: Mohammadamin Barekatain | ||
| affiliation: [1, 2] | ||
| url: http://barekatain.me/ | ||
| position: intern | ||
| - name: Mai Nishimura | ||
| - name: Ryo Yonetani | ||
| affiliation: [1] | ||
| position: Senior Researcher | ||
| url: https://denkiwakame.github.io | ||
| - name: Tadashi Kozuno | ||
| url: https://yonetaniryo.github.io/ | ||
| - name: Masashi Hamaya | ||
| affiliation: [1] | ||
| position: Senior Researcher | ||
| url: https://sites.google.com/view/masashihamaya/home | ||
| # - name: Mai Nishimura | ||
| # affiliation: [1] | ||
| # url: https://denkiwakame.github.io | ||
| # - name: Asako Kanezaki | ||
| # affiliation: [2] | ||
| # url: https://kanezaki.github.io/ | ||
| contact_ids: ['github', 'omron', 2] #=> github issues, [email protected], 2nd author | ||
| contact_ids: ['github', 'omron'] #=> github issues, [email protected], 2nd author | ||
| affiliations: | ||
| - OMRON SINIC X Corporation | ||
| - Technical University of Munich | ||
|
|
@@ -64,185 +58,19 @@ header: | |
|
|
||
| teaser: teaser.png | ||
| overview: | | ||
| This is a versatile template designed to satisfy your research project page needs, all while harnessing the power of **UIKit** and **React**. Built on the foundations of simplicity and flexibility, this template allows you to focus on expressing your ideas without the hassle of directly handling CSS—thanks to customizable SASS variables. | ||
| With markdown as your canvas and $\KaTeX$ for precise equations, crafting clear and engaging project page becomes effortless. Whether you're unraveling complex theories or presenting your findings, this template aims to support your scholarly endeavors with grace and ease. | ||
| *Need to edit HTML directly?* Fear not! In addition to markdown, you can also directly write HTML with ease. Feel empowered to craft your content exactly as you envision it, whether through markdown's simplicity or the precision of HTML. | ||
| Transfer reinforcement learning (RL) aims at improving learning efficiency of an agent by exploiting knowledge from other source agents trained on relevant tasks. However, it remains challenging to transfer knowledge between different environmental dynamics without having access to the source environments. In this work, we explore a new challenge in transfer RL, where only a set of source policies collected under unknown diverse dynamics is available for learning a target task efficiently. To address this problem, the proposed approach, *MULTI-source POLicy AggRegation (MULTIPOLAR)*, comprises two key techniques. We learn to aggregate the actions provided by the source policies adaptively to maximize the target task performance. Meanwhile, we learn an auxiliary network that predicts residuals around the aggregated actions, which ensures the target policy”s expressiveness even when some of the source policies perform poorly. We demonstrated the effectiveness of MULTIPOLAR through an extensive experimental evaluation across six simulated environments ranging from classic control problems to challenging robotics simulations, under both continuous and discrete action spaces. | ||
| body: | ||
| - title: Media examples | ||
| text: | | ||
| You can access media files in `public` directly like: `<img src="method.png" />` | ||
| <img src="method.png" alt="" /> | ||
| See also [UIKit Video Components Documentation](https://getuikit.com/docs/video) and [Grid system](https://getuikit.com/docs/grid) | ||
| <div class="uk-child-width-1-2@m" uk-grid> | ||
| <div> | ||
| <video | ||
| src="demo.mp4" | ||
| loop | ||
| muted | ||
| uk-video="autoplay:inview" | ||
| /> | ||
| </div> | ||
| <div> | ||
| <video | ||
| src="demo.mp4" | ||
| loop | ||
| muted | ||
| uk-video="autoplay:inview" | ||
| /> | ||
| </div> | ||
| </div> | ||
| - title: Markdown examples | ||
| text: | | ||
| Here's our demo text showcasing the power of markdown and KaTeX integration! | ||
| Markdown allows you to easily format text using simple syntax. | ||
| - **bold** | ||
| - *italic* | ||
| - `inline code`. | ||
| You can also create headings of various levels: | ||
| # Heading Level 1 | ||
| ## Heading Level 2 | ||
| ### Heading Level 3 | ||
| #### Heading Level 4 | ||
| Markdown allows you to create tables like the following: | ||
| #### Motion Planning (MP) Dataset | ||
| markdown version | ||
| |Method|Opt|Exp|Hmean| | ||
| |--|--|--|--| | ||
| |BF| 65.8 (63.8, 68.0)| 44.1 (42.8, 45.5) | 44.8 (43.4, 46.3)| | ||
| |WA*| 68.4 (66.5, 70.4)| 35.8 (34.5, 37.1) | 40.4 (39.0, 41.8)| | ||
| |**Neural A*** | **87.7 (86.6, 88.9)**| 40.1 (38.9, 41.3) | 52.0 (50.7, 53.3)| | ||
| Of course, you can also directly write tables in HTML if needed. For more details, refer to the [UIKit Table documentation](https://getuikit.com/docs/table). | ||
| <h4>Motion Planning (MP) Dataset</h4> | ||
| <p>HTML version</p> | ||
| <div class="uk-overflow-auto"> | ||
| <table class="uk-table uk-table-small uk-text-small uk-table-divider"> | ||
| <thead> | ||
| <tr> | ||
| <th>Method</th> | ||
| <th>Opt</th> | ||
| <th>Exp</th> | ||
| <th>Hmean</th> | ||
| </tr> | ||
| </thead> | ||
| <tbody> | ||
| <tr> | ||
| <td> | ||
| BF | ||
| <br /> | ||
| WA* | ||
| </td> | ||
| <td> | ||
| 65.8 (63.8, 68.0) | ||
| <br /> | ||
| 68.4 (66.5, 70.4) | ||
| </td> | ||
| <td> | ||
| 44.1 (42.8, 45.5) | ||
| <br /> | ||
| 35.8 (34.5, 37.1) | ||
| </td> | ||
| <td> | ||
| 44.8 (43.4, 46.3) | ||
| <br /> | ||
| 40.4 (39.0, 41.8) | ||
| </td> | ||
| </tr> | ||
| <tr> | ||
| <td> | ||
| SAIL | ||
| <br /> | ||
| SAIL-SL | ||
| <br /> | ||
| BB-A* | ||
| </td> | ||
| <td> | ||
| 5.7 (4.6, 6.8) | ||
| <br /> | ||
| 3.1 (2.3, 3.8) | ||
| <br /> | ||
| 31.2 (28.8, 33.5) | ||
| </td> | ||
| <td> | ||
| 58.0 (56.1, 60.0) | ||
| <br /> | ||
| 57.6 (55.7, 59.6) | ||
| <br /> | ||
| 52.0 (50.2, 53.9) | ||
| </td> | ||
| <td> | ||
| 7.7 (6.4, 9.0) | ||
| <br /> | ||
| 4.4 (3.5, 5.3) | ||
| <br /> | ||
| 31.1 (29.2, 33.0) | ||
| </td> | ||
| </tr> | ||
| <tr class="uk-active"> | ||
| <td> | ||
| Neural BF | ||
| <br /> | ||
| <b>Neural A*</b> | ||
| </td> | ||
| <td> | ||
| 75.5 (73.8, 77.1) | ||
| <br /> | ||
| <b>87.7 (86.6, 88.9)</b> | ||
| </td> | ||
| <td> | ||
| 45.9 (44.6, 47.2) | ||
| <br /> | ||
| 40.1 (38.9, 41.3) | ||
| </td> | ||
| <td> | ||
| 52.0 (50.7, 53.4) | ||
| <br /> | ||
| 52.0 (50.7, 53.3) | ||
| </td> | ||
| </tr> | ||
| </tbody> | ||
| </table> | ||
| </div> | ||
| <h3>Selected Path Planning Results</h3> | ||
| <img | ||
| src="assets/result1.png" | ||
| class="uk-align-center uk-responsive-width" | ||
| alt="" | ||
| /> | ||
| <h3>Path Planning Results on SSD Dataset</h3> | ||
| <img | ||
| src="assets/result2.png" | ||
| class="uk-align-center uk-responsive-width" | ||
| alt="" | ||
| /> | ||
| - title: KaTeX examples | ||
| text: > | ||
| $\KaTeX$ enables you to write mathematical expressions beautifully within your text (e.g. $\alpha$, $\beta$, $\gamma$ ). | ||
| $$ax^2 + bx + c = 0$$ | ||
| $$ \int \oint \sum \prod $$ | ||
| $$ \begin{CD} A @>a>> B \\ @VbVV @AAcA \\ C @= D \end{CD} $$ | ||
| [KaTeX supports a wide range of mathematical symbols and equations](https://katex.org/docs/support_table.html), ensuring your technical content is both clear and visually appealing. | ||
| With markdown for text formatting and KaTeX for mathematical expressions, our template empowers you to communicate complex ideas effectively. Whether you're writing a scientific paper or a technical blog post, harnessing these tools will elevate your content and engage your readers. | ||
| body: null | ||
| projects: | ||
| - title: 'maru: a miniature-sized wheeled robot for swarm robotics research' | ||
| journal: "CHI'24" | ||
| img: https://getuikit.com/docs/images/light.jpg | ||
| description: | | ||
| "maru" (= miniature assemblage adaptive robot unit) is a custom-made, miniature-sized, two-wheeled robot designed specifically for tabletop swarm robotics research. | ||
| url: https://github.com/omron-sinicx/swarm-body | ||
| - title: 'Language-Guided Pattern Formation for Swarm Robotics with Multi-Agent Reinforcement Learning' | ||
| journal: "IROS'24" | ||
| img: https://omron-sinicx.github.io/language-guided-pattern-formation/assets/teaser.png | ||
| - title: 'TRANS-AM: Transfer Learning by Aggregating Dynamics Models for Soft Robotic Assembly”, International Conference on Robotics and Automation' | ||
| journal: "ICRA'21'" | ||
| img: https://kazutoshi-tanaka.github.io/pages/teaser.png | ||
| description: | | ||
| "maru" (= miniature assemblage adaptive robot unit) is a custom-made, miniature-sized, two-wheeled robot designed specifically for tabletop swarm robotics research. | ||
| url: https://github.com/omron-sinicx/swarm-body | ||
| - title: 'Language-Guided Pattern Formation for Swarm Robotics with Multi-Agent Reinforcement Learning' | ||
| journal: "IROS'24" | ||
| img: method.png | ||
| TRANS-AM is a transfer reinforcement learning method that improves sample efficiency by adaptively aggregating dynamics models from source environments, enabling robots to quickly adapt to unseen tasks with fewer episodes. | ||
| url: https://kazutoshi-tanaka.github.io/pages/transam.html | ||
| - title: Adaptive Distillation for Decentralized Learning from Heterogeneous Clients | ||
| journal: "ICPR'20" | ||
| img: icpr20.png | ||
| description: | | ||
| "maru" (= miniature assemblage adaptive robot unit) is a custom-made, miniature-sized, two-wheeled robot designed specifically for tabletop swarm robotics research. | ||
| url: https://github.com/omron-sinicx/swarm-body | ||
| a new decentralized learning method that aggregates diverse client models using adaptive distillation to train a high-performance global model, demonstrated to be effective across multiple datasets. | ||
| url: https://arxiv.org/abs/2008.07948 | ||